mlsanityData to 7 Oct 2026

Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography

arXiv 1908.06948 ↗First posted 16 Aug 2019eess.IVcited by 243

Not on the map. Why?

Abstract (arXiv)

Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis. Over the past decades, the automation of this task has been the subject of intense research. In this paper, we evaluate how far the state-of-the-art encoder-decoder deep convolutional neural network methods can go at assessing 2D echocardiographic images, i.e segmenting cardiac structures as well as estimating clinical indices, on a dataset especially designed to answer this objective. We therefore introduce the Cardiac Acquisitions for Multi-structure Ultrasound Segmentation (CAMUS) dataset, the largest publicly-available and fully-annotated dataset for the purpose of echocardiographic assessment. The dataset contains two and four-chamber acquisitions from 500 patients with reference measurements from one cardiologist on the full dataset and from three cardiologists on a fold of 50 patients. Results show that encoder-decoder based architectures outperform state-of-the-art non-deep learning methods and faithfully reproduce the expert analysis for the end-diastolic and end-systolic left ventricular volumes, with a mean correlation of 0.95 and an absolute mean error of 9.5 ml. Concerning the ejection fraction of the left ventricle, results are more contrasted with a mean correlation coefficient of 0.80 and an absolute mean error of 5.6 %. Although these results are below the inter-observer scores, they remain slightly worse than the intra-observer's ones. Based on this observation, areas for improvement are defined, which open the door for accurate and fully-automatic analysis of 2D echocardiographic images.

Key facts. Cited by 243 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 14; 2023: 36; 2024: 52; 2025: 71; 2026: 58.

243 papers.

Sort:

By area:

  1. 2023UniverSeg: Universal Medical Image Segmentationcited by 90
  2. 2025MedSAM2: Segment Anything in 3D Medical Images and Videoscited by 88
  3. 2023A Review of Uncertainty Estimation and its Application in Medical Imagingcited by 59
  4. 2023ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Imagecited by 47
  5. 2024Segment Anything in Medical Images and Videos: Benchmark and Deploymentcited by 42
  6. 2023Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Promptingcited by 40
  7. 2023Segment Anything Model for Medical Images?cited by 39
  8. 2025nnInteractive: Redefining 3D Promptable Segmentationcited by 39
  9. 2023Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentationcited by 33
  10. 2021Echocardiography Segmentation with Enforced Temporal Consistencycited by 30
  11. 2021A Systematic Collection of Medical Image Datasets for Deep Learningcited by 29
  12. 2023Exploring Transfer Learning in Medical Image Segmentation using Vision-Language Modelscited by 28
38 more
  1. 2024Segment anything model 2: an application to 2D and 3D medical imagescited by 27
  2. 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Qualitycited by 24
  3. 2024UltraSam: A Foundation Model for Ultrasound using Large Open-Access Segmentation Datasetscited by 23
  4. 2023GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentationcited by 22
  5. 2024Tyche: Stochastic In-Context Learning for Medical Image Segmentationcited by 20
  6. 2023Dehazing Ultrasound using Diffusion Modelscited by 17
  7. 2021Adaptive Contrast for Image Regression in Computer-Aided Disease Assessmentcited by 16
  8. 2024Is SAM 2 Better than SAM in Medical Image Segmentation?cited by 16
  9. 2025USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencodingcited by 16
  10. 2021A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiogramscited by 15
  11. 2023OpenForest: A data catalogue for machine learning in forest monitoringcited by 15
  12. 2023Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registrationcited by 14
  13. 2024EchoFM: Foundation Model for Generalizable Echocardiogram Analysiscited by 14
  14. 2024From Pretraining to Privacy: Federated Ultrasound Foundation Model with Self-Supervised Learningcited by 14
  15. 2025Flow Matching Meets Biology and Life Science: A Surveycited by 14
  16. 2021FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imagingcited by 13
  17. 2022Contrastive Pretraining for Echocardiography Segmentation with Limited Datacited by 12
  18. 2022Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videoscited by 12
  19. 2025Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Modelscited by 12
  20. 2022Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Datacited by 11
  21. 2024VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blockscited by 11
  22. 2024CC-SAM: SAM with Cross-feature Attention and Context for Ultrasound Image Segmentationcited by 11
  23. 2024EchoApex: A General-Purpose Vision Foundation Model for Echocardiographycited by 11
  24. 2024CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videoscited by 11
  25. 2024MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidancecited by 11
  26. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  27. 2022CRISP - Reliable Uncertainty Estimation for Medical Image Segmentationcited by 10
  28. 2025UniBiomed: A Universal Foundation Model for Grounded Biomedical Image Interpretationcited by 10
  29. 2022Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo viewscited by 9
  30. 2023Attention Mechanisms in Medical Image Segmentation: A Surveycited by 9
  31. 2023Adaptive Correspondence Scoring for Unsupervised Medical Image Registrationcited by 9
  32. 2024Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generationcited by 9
  33. 2024Robust Box Prompt based SAM for Medical Image Segmentationcited by 9
  34. 2025A Fully Open and Generalizable Foundation Model for Ultrasound Clinical Applicationscited by 9
  35. 2022Label-free segmentation from cardiac ultrasound using self-supervised learningcited by 8
  36. 2023FPUS23: An Ultrasound Fetus Phantom Dataset with Deep Neural Network Evaluations for Fetus Orientations, Fetal Planes, and Anatomical Featurescited by 8
  37. 2024Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learningcited by 8
  38. 2024CoReEcho: Continuous Representation Learning for 2D+time Echocardiography Analysiscited by 8

50 most cited of 243 All 243 (JSON)